Daniel Scalena on Mythryl: “I'd never have guessed models commit to their final answer this…”

I'd never have guessed models commit to their final answer this early, often within the first 20% of reasoning, across math/logic tasks and model families. The rest is mostly hedging that doesn't change their mind. And turns out they encode this internally, we can decode it! 🧵👇

Sara Candussio@saracandussio.bsky.social

Are all the CoT steps necessary? In our latest paper, we find evidence for the existence of a commitment boundary, marking a sharp transition from no/mid guesses to the model final answer across various reasoning tasks and model families. Thread 🧵👇

1/7/26, 12:40 pm3 reposts9 likes

Post